Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vignesh2027/AI-AGENT-SKILLS --skill incident-responsegit clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLSWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vignesh2027/ai-agent-skills/incident-response)<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/incident-response"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/incident-response/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/incident-response"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/incident-response.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00993 |
| Opus 5 | $0.00009 | $0.00496 |
| Sonnet 5 | $0.00004 | $0.00199 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
incident-response scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Incidents are inevitable. How you respond determines whether they are learning opportunities or recurring nightmares. This skill gives you a structured process from first alert to prevention of recurrence.
When to Use
- When an alert fires indicating user impact
- When a deployment causes degraded service
- When you discover a data issue in production
- After any unplanned outage, even brief
Process
Phase 1: DETECT (0–5 minutes)
Step 1: Acknowledge the alert Acknowledge in your alerting system within 5 minutes. This signals you're on it and stops duplicate escalations.
Step 2: Assess severity
- P0 — Complete service outage, data loss, security breach. Page everyone.
- P1 — Significant degradation affecting many users. Page the team.
- P2 — Partial degradation, workaround exists. Handle during business hours.
- P3 — Minor issue, users unaffected or workaround obvious. Normal ticket.
Step 3: Declare the incident and open a channel For P0/P1: open an incident channel (#incident-YYYY-MM-DD-brief-description). All communication goes there. Appoint an Incident Commander (IC).
Phase 2: COMMUNICATE (5–15 minutes)
Step 4: Post a status update Within 15 minutes of detection, post to the status page: "We are investigating reports of [symptom]. We will provide an update in 30 minutes." Do not wait until you have a fix. Users need to know you know.
Step 5: Brief stakeholders Notify: on-call manager, customer-facing teams, affected customers (for P0/P1). Use the incident channel as the single source of truth.
Phase 3: MITIGATE (15 minutes – resolution)
Step 6: Stop the bleeding first Mitigation before diagnosis. Options:
- Roll back the last deployment
- Disable the feature flag
- Scale up capacity
- Redirect traffic away from the failing component
Don't spend time diagnosing the root cause while users are impacted. Mitigate first.
Step 7: Diagnose Once impact is reduced, find the root cause:
- What changed recently? (Deployments, config changes, traffic spikes)
- What do the metrics show? (Error rate, latency, saturation)
- What do the logs show? (First error, error pattern, affected user IDs)
- What do the traces show? (Where in the call chain is the failure?)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 105 lines · 0 tokens per session scan A 13ae65799a8e
incident-response is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 13d ago), licensed MIT. It adds 18 tokens to every session and 993 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cce-routing
Use Cursor Bridge's read-only cursorcontextengine for unfamiliar project understanding when the exact code location is unknown or the task requires tracing behavior, symbols, callers and callees, data flow, registrations, interface implementations, ownership boundaries, or cross-module relationships. Trigger for…
gh-fix-ci
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use gh to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.
sentry
Query Sentry organizations, projects, and unresolved issues/errors via the Sentry API. Use when the user asks about Sentry errors, issues, or projects.
signoz
Query observability (services, traces, logs, metrics) from a SigNoz instance via its API. Use when the user asks about app performance, errors, latency, or telemetry in SigNoz.
fix-default
A default procedure for handling bug fixes, organised as a three-step scan and a CP process. The input does not explain what the three steps or CP process contain.
rel-ai-debugging
Use when repository behavior is reproducibly wrong and needs causal diagnosis or repair, including errors, broken tests, crashes, regressions, failed contracts, or incorrect runtime behavior. Do not use for general audits or final verification when no active defect is being diagnosed.